Benchmark Leaderboards
Loading leaderboardsβ¦
Loading leaderboardsβ¦
Track which models hold the current SOTA on the benchmarks the field actually uses. Click a column header to sort; the leading row is highlighted.
GIFT-Eval probabilistic-forecasting board β aggregate CRPS (Continuous Ranked Probability Score) across the 23 GIFT-Eval datasets; lower is better. Measures probabilistic (distributional) forecast quality rather than point-forecast error.
Metric: CRPS β lower is better Β· Source β